Metraipolis › archive › dc_7fa935a4dfa4
Multi-Access Speculative Inference: Uplink or Downlink? — arXiv:2608.29618
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29618
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:38:51.293Z
- SHA-256 of the archived text
0bc76168e74f37dd8b998617493f5f293fcadc95c26993e1ca7510a4f5a5b11d- Stable URL of this page
https://metraipolis.com/documento/dc_7fa935a4dfa4
How to cite
Multi-Access Speculative Inference: Uplink or Downlink? — arXiv:2608.29618 — arXiv (en), https://arxiv.org/abs/2608.29618 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7fa935a4dfa4 (Metraipolis archive dc_7fa935a4dfa4, sha256 0bc76168e74f37dd8b998617493f5f293fcadc95c26993e1ca7510a4f5a5b11d)
BibTeX
@misc{dc7fa935a4dfa4,
title = {Multi-Access Speculative Inference: Uplink or Downlink? — arXiv:2608.29618},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29618},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7fa935a4dfa4; sha256 0bc76168e74f37dd8b998617493f5f293fcadc95c26993e1ca7510a4f5a5b11d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29618. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-access speculative inference (Multi-SPIN) extends SPIN to multi-device edge networks to accelerate cooperative token generation. It allows on-device small language models (SLMs) to autoregressively draft multiple tokens for individual generation tasks, while an edge-server large language model (LLM) verifies them in parallel. The major communication overhead arises when a drafted token is rejected by the server, in which case sampling the correction token requires access to both the SLM-output draft distribution and the LLM-output target distribution over the full token vocabulary. Existing designs typically perform correction at the server by uploading the draft distribution, but transmitting a vocabulary-wide distribution creates a critical uplink (UL) bottleneck. Alternatively, the correction can be performed at the device by downloading the target distribution, leveraging the high transmission rates available on the downlink (DL). Motivated by this insight, we introduce communication-mode selection as a new design dimension for Multi-SPIN. Specifically, each device can adaptively switch between the UL and DL modes to balance the UL bottleneck against the shared DL resource constraint, thereby relieving the overall communication burden. We formulate a sum-token-goodput maximization problem that jointly accounts for mode selection, draft-length control, and power allocation. For mode selection, we reveal a simple optimal structure that enables efficient search over the number of UL devices, with the corresponding transmit powers optimized accordingly. For draft-length control, we develop a greedy-search algorithm that adapts device-specific draft lengths to heterogeneous computation and communication capabilities. Experimental results on Qwen2.5 and DeepSeek-R1 model pairs demonstrate that the proposed framework significantly improves token goodput. Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-01 in math.IT). Categorie arXiv: Information Theory (cs.IT). Pagina del lavoro: https://arxiv.org/abs/2608.29618 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T09:10:18.068Z dalla pagina https://arxiv.org/catchup/math.IT/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).